Robot Programming by Demonstration

By Krishna Kumar Narayanan, Luis-Felipe Posada, Frank Hoffmann, Torsten Bertram. 2010

928 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Reinforcement Learning

Citations in the corpus

One-Shot Imitation Learning (2017, background): “Survey articles include (Schaal, 1999; Calinon, 2009; Argall et al., 2009).”
Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, neutral): “…many goals/tasks in a parameterized task space) before focusing on different ways to perform the same tasks (here this means finding several alternative actions to achieve the same goal), knowledge-based exploration techniques like RIAC cannot be efficient in robots with redundant forward models.”
Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations (2020, background): “Imitation learning has been applied to multiple domains such as playing table tennis [22], Go [37] and video games [33], and driving autonomously [4, 31] In robotics, the idea of robots learning from human demonstrations have been extensively explored [36, 17, 23, 11, 14, 3, 5].”
Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control (2021, background): “Imitation learning (IL) has been widely studied in the context of robotic manipulation tasks [2, 4, 5, 11, 31].”
Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation (2017, methodology): “Imitation learning is a class of methods for acquiring skills by observing demonstrations (see, e.g., [1], [2], [3] for surveys).”
Third-Person Imitation Learning (2017, background): “Imitation learning has a long history, with several good survey articles, including (Schaal, 1999; Calinon, 2009; Argall et al., 2009).”
Robust Imitation of Diverse Behaviors (2017, background): “We cannot cover this literature at the level of detail it deserves, and instead refer readers to recent authoritative surveys on the topic [5, 1, 14].”
Unsupervised Perceptual Rewards for Imitation Learning (2016, background): “to overcome the challenging problem of learning robotic tasks from scratch [7] (also see [3] for a survey).”
Spatial adaption of robot trajectories based on laplacian trajectory editing (2015, methodology): “In the latter case programming by demonstration (PbD) (Billard et al. 2008) is a standard method for teaching a robot complex movements.”
AppAgent: Multimodal Agents as Smartphone Users (2023, positive): “PbD has been widely applied in robotics, enabling robots to perform complex tasks by replicating demonstrated actions [2, 5].”
A survey of robot learning from demonstration (2009, neutral): “For example, one proposed categorization considers the broad spectrum of who, what, when and how to imitate, or subsets thereof [2] [3].”
Audio-visual classification and detection of human manipulation actions (2014, background): “However in the context of robot learning from demonstration it is meaningful to focus the attention on descriptive features that encodes how objects are being used by a human [20], [21] to achieve a task.”
Instructable Intelligent Personal Agent (2016, background): “Billard et al. (2008) state that learning by demonstration has three advantages, the ﬁrst is that demonstration reduces the search space for the robot, allowing the robot to ﬁnd the way to perform the task.”
Dynamical System Modulation for Robot Learning via Kinesthetic Demonstrations (2008, background): “In order to address this last issue, programming by demonstration (PbD) has emerged as a promising approach [1].”
Learning Generalizable Control Programs (2011, result): “This approach is in direct contrast to much of the recent work in robot learning that focuses on programming by demonstration [3] and imitation learning [31].”
Adversarial Imitation Learning from State-only Demonstrations (2019, neutral): “One well-known way in which artificially-intelligent agents are able to learn to perform tasks is via imitation learning [1, 2, 9], where agents attempt to learn a task by observing another, more expert agent perform that task.”
Learning bimanual end-effector poses from demonstrations using task-parameterized dynamical systems (2015, background): “Programming by demonstration (PbD) has gained high interest in Robotics as an intuitive and user-friendly means to transfer skills from humans to robots [1], [2].”
Multilateral surgical pattern cutting in 2D orthotropic gauze with deep reinforcement learning policies for tensioning (2017, background): “These approaches are broadly classified under the category of Learning From Demonstrations (LfD) [3, 8], where demonstration trajectories are directly modified for generalizing to test situations.”